CN106441319A - A system and method for generating a lane-level navigation map of an unmanned vehicle - Google Patents

Abstract

The invention relates to a system and method for generating a lane-level navigation map of an unmanned vehicle based on multi-source data, including two parts: an offline global map and an online local map. The offline module refers to the target area where the unmanned vehicle is driving , use satellite photos (or aerial photos), vehicle sensors (lidar and camera), high-precision combined positioning system (satellite positioning system and inertial navigation system) to obtain the original road data, and then process the original road data offline to extract A variety of road information, and finally fuse the road information extraction results to generate an offline global map. Offline global maps are stored in a hierarchical structure. The online module refers to that when the unmanned vehicle drives automatically in the target area, according to the real-time positioning information, the road data in the offline global map is extracted, and an online local map centered on the vehicle and within a fixed distance range is drawn. The invention can be applied in fusion perception, high-precision positioning and intelligent decision-making of unmanned vehicles.

Description

A system and method for generating a lane-level navigation map of an unmanned vehicle

technical field

The invention belongs to the technical field of unmanned vehicles, and in particular relates to a system and method for generating a lane-level high-precision navigation map for unmanned vehicles based on multi-source data.

Background technique

At present, the research and development of unmanned vehicles and key technologies is in the ascendant. More and more domestic and foreign automobile manufacturers, IT companies, universities, research institutes, etc. are investing a lot of manpower and material resources to actively promote unmanned vehicles and auxiliary vehicles. R&D and commercialization of driving systems, intelligent connected vehicles, etc. In recent years, Audi, Mercedes-Benz, GM, Ford, Toyota, Nissan, SAIC, Tesla and many other domestic and foreign automakers, as well as technology companies such as Google, have tried to put their driverless vehicles on the market around 2020.

The high-precision electronic map is one of the key factors to promote the development of unmanned vehicles. Ordinary navigation maps have low precision and a small amount of information, and can only provide geographic information with road-level precision, without specific lane information, road feature information, and other data. With the development and application of advanced driver assistance systems and unmanned vehicles, lane-level high-precision maps have been used more and more. After obtaining a high-precision map, the unmanned vehicle does not need to sense the surrounding environment in real time to build a local map and move forward while exploring. Instead, it only needs to accurately match the vehicle to the electronic map according to the perceived surrounding environment. Make the decision-making system make the right decision. The introduction of electronic maps will undoubtedly reduce the cost and detection requirements of the perception system, which is conducive to the promotion of driverless technology. On the other hand, with the electronic map, the decision-making system can plan the movement path in advance, choose the most reasonable lane to drive, and improve the intelligence and comfort of the vehicle.

At present, there are other methods for the collection and production of high-precision maps, such as the method of taking pictures. The cost of taking pictures is low and the operation is convenient. large deviation. Using the method of making multi-source data, the advantages of various methods can be integrated, and maps can be collected and generated under various road conditions.

The Chinese patent with publication number CN104089619A (application number 201410202876.4) provides an accurate matching system for GPS navigation maps of unmanned vehicles. The system uses the GPS navigation system to collect all the road information, makes a KML text map, and matches the GPS information with the text map to correct the positioning error during driving. Only GPS positioning information is used in the production and use of the patented map, the data source is single, and the characteristic information on the road is not used. It cannot be implemented in scenarios where GPS signals are interfered, such as tunnels and buildings.

The Chinese patent with publication number CN104573733A (application number 201410838713.5) provides a high-definition map generation system and method based on high-definition orthophoto maps. The method uses the vehicle-mounted image capture module to collect road images to obtain an orthophoto map, and combines the corresponding geographic information files to generate a global map base map, and further labels various geographic information data. This method will cause large deviations in the obtained map base map when the road is uneven, and the camera itself is distorted, the field of view is limited, and the globality is not good enough.

Contents of the invention

The technical problem of the present invention is to overcome the deficiencies of the prior art and provide a method for generating a lane-level navigation map for unmanned vehicles based on multi-source data. The present invention can combine the advantages of various map collection methods, in various High-precision maps can be obtained under road conditions, and the generated electronic maps are rich in information, which can support lane-level high-precision positioning, path planning, and intelligent decision-making.

In order to achieve the above object, the present invention adopts the following technical solutions:

The invention provides a system for generating a lane-level navigation map of an unmanned vehicle, comprising:

The offline module uses a variety of data collection methods to obtain the original road data in the target area of the unmanned vehicle, and after offline processing, extracts a variety of road information, and then fuses the extracted results to generate an offline global map;

In the online module, during the automatic driving process of the vehicle in the target area, the road data in the offline global map is extracted according to the real-time positioning information, and an online local map centered on the vehicle and within a fixed distance range is drawn.

The source of the original road data in the offline module includes: satellite photos or aerial photos, vehicle sensors, high-precision integrated positioning system, vehicle-mounted sensors include laser radar and camera, and high-precision integrated positioning system includes satellite positioning system and inertial navigation system; wherein Satellite photos are used to obtain the topological relationship between roads, road length, number of lanes, lane width, road attribute information, lane lines, and stop road surface identification information; lidar is used to detect the position and height of road edges; cameras are used to detect lanes The width and color of the line; the high-precision combined positioning system is used to obtain the position and heading information of the vehicle at a certain moment and the driving track information within a certain period of time.

The extraction process of road information in the offline module includes two kinds:

The first one is manual extraction using map labeling software;

The second is to use algorithms to automatically detect and manually confirm the detection results, remove false detection results, and complete missed detection results.

The offline global map is stored in a hierarchical structure, with a total of two layers, and each layer of data is related to each other, namely:

The first layer is road-level navigation information, including road attribute information such as topological relationship between roads, road length, number of lanes, and lane width;

The second layer, lane-level navigation information, includes lane attribute information such as various road signs in each road segment, position and height of road edges, width and color of lane lines, and vehicle trajectory information.

The online local map in the online module is a grid map with a width of 500 and a height of 750, where each grid represents a 20cm*20cm square in the actual road scene; the center of the vehicle is located at (250, 500) of the grid map coordinate system , the range of the drawn local map is 100 meters in front of the vehicle, 50 meters behind, and 50 meters on the left and right sides respectively.

The invention provides a method for generating a lane-level navigation map of an unmanned vehicle, and the specific steps are as follows:

Step 1. Obtain satellite photos or aerial photos with geographic location information, and manually extract road information on relevant map labeling software. The satellite photos can be obtained free of charge or purchased from relevant satellite photo providers, and the aerial photos can be purchased from relevant aerial photo providers or obtained by using a small aerial camera. Map labeling software can be free map software (such as Google Earth software) or paid map software, or self-developed satellite map geographic information labeling software. The road information that needs to be extracted includes the starting waypoint and middle waypoint of each road segment in the target area of the driverless vehicle, the topological relationship between roads, road width, road length, road shape, number of lanes, lane width, Road attribute information such as lane type, and white solid line, white dashed line, yellow solid line, yellow dashed line, lane stop line, sidewalk, road median, grid line, diamond-shaped deceleration sign, straight arrow, left turn in each road Arrows, right-turn arrows, U-turn arrows, parking spaces and other road marking information;

Step 2. Manually driving the unmanned vehicle to drive in the target area, using on-board sensors (lidar and camera) and high-precision combined positioning system (satellite positioning system and inertial navigation system) to collect raw road data;

Step 3. Use the lidar data and camera data collected by the vehicle to automatically detect the relevant feature information of the road offline, and manually confirm the detection results, remove the false detection results, and complete the missed detection results. The lidar data is used to detect the position and height of the road edge, and the camera data is used to detect the width and color of the lane line;

Step 4. Using the positioning data collected by the vehicle on the target road section, after smoothing with the extended Kalman filter, the jump of the positioning signal is removed, and the driving track of the vehicle on a certain lane is generated;

Step 5. Combine the results obtained in Step 1, Step 3, and Step 4 to generate a global offline map. The road attribute information obtained in step 1, the road edge and lane line information obtained in step 3 are used to generate the first layer of the map; the road surface identification information obtained in step 1, and the vehicle trajectory information obtained in step 4 are used to generate the first layer of the map second floor. The data in the second layer of the map is associated with the data in the first layer according to its geographic location;

Step 6. During the automatic driving process of the unmanned vehicle in the target area, according to the real-time positioning information, the road data in the offline global map is extracted, and the vehicle is centered, 100 meters in front, 50 meters behind, and 50 meters on the left and right. Online local maps within meters.

Compared with the prior art, the present invention has the following beneficial effects: the main problem of the prior art is that the data source of the navigation map is single, which can only be applied to some specific environments, and the generated navigation map data is not sufficient enough to support Lane-Level Decision Planning for Autonomous Vehicles. The innovation of the present invention lies in that various devices are used as data sources, and the extraction results of various road information are fused to generate a navigation map, so the applicability is wide and the map data is detailed and rich.

(1) The present invention utilizes multiple devices including satellite photos, laser radars, cameras, combined positioning systems, etc. Navigation maps for unmanned vehicles that are required for a wide range of applications;

(2) The map collected and generated by the present invention has the accuracy of the lane level, which can make the vehicle always be matched and positioned in the predetermined lane under ideal conditions, and realize high-precision positioning of the lane level;

(3) The map collected and generated by the present invention includes lane attribute information such as road surface markings, road edge positions and heights, etc., and can realize online road environment perception based on prior information and lane-level intelligent decision-making based on traffic rules.

Description of drawings

Other characteristics, objects and advantages of the present invention will become more apparent from the description of non-limiting embodiments with reference to the following drawings:

Fig. 1 is the flow chart of the method for generating an unmanned vehicle lane-level navigation map of the present invention;

Fig. 2 is a schematic diagram of an example installation and configuration method of a vehicle-mounted sensor;

Fig. 3 is a schematic diagram of a certain area in the offline global map of Hefei;

Figure 4 is an enlarged view of a certain intersection in the offline global map of Hefei;

In the figure: laser radar 1, camera 2, high-precision integrated positioning system signal receiving antenna 3.

detailed description

The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

A system for generating lane-level navigation maps for unmanned vehicles, as shown in Figure 1, includes:

The offline module uses a variety of data collection methods to obtain the original road data in the target area of the unmanned vehicle, and after offline processing, extracts a variety of road information, and then fuses the extracted results to generate an offline global map;

In the online module, during the automatic driving process of the vehicle in the target area, the road data in the offline global map is extracted according to the real-time positioning information, and an online local map centered on the vehicle and within a fixed distance range is drawn.

The original road data sources in the offline module include:

Satellite photos are used to extract the starting waypoint and middle waypoint of each road segment in the target area of unmanned driving vehicles, the topological relationship between roads, road width, road length, road shape, number of lanes, lane width, Road attribute information such as lane type, and white solid line, white dashed line, yellow solid line, yellow dashed line, lane stop line, sidewalk, road median, grid line, diamond-shaped deceleration sign, straight arrow, left turn in each road Arrows, right-turn arrows, U-turn arrows, parking spaces and other road marking information;

LiDAR to detect the location and height of road edges. In this embodiment, the laser radar adopts the HDL-64E high-precision laser radar of Velodyne Company. The lidar is installed in front of the roof, which can sense and construct the three-dimensional scene around the vehicle in real time, and detect information such as road edges and obstacles;

A camera to detect the width and color of lane lines. In this embodiment, the camera adopts the DFK23G274 industrial camera of Yingmeijing Company. The camera is installed on the inside of the windshield, where the rearview mirror is located;

The high-precision combined positioning system is used to obtain the position and heading information of the vehicle at a certain moment and the driving track information within a certain period of time. In this embodiment, the integrated positioning system adopts the inertial integrated navigation system SPAN-CPT of NovAtel Company, which has the advantages of high positioning accuracy and good anti-interference, and can meet the application requirements of the present invention. The signal receiving antenna of the combined positioning system is located at the rear of the roof.

Figure 2 is a schematic diagram of the installation and configuration of the laser radar, camera and combined positioning system signal receiving antenna in the vehicle in this embodiment, wherein the laser radar 1 is used to detect the edge of the road, the camera 2 is used to detect lane lines, and the combined positioning system signal reception Antenna 3 is used to receive positioning signals.

A method for generating a lane-level navigation map of an unmanned vehicle, the specific implementation steps are as follows:

Step 1. Use Google Earth software to obtain satellite photos of the target driving area of the unmanned vehicle, and use the "Add Path" function of the software to manually extract road information. The road information that needs to be extracted includes the starting waypoint and middle waypoint of each road segment in the target area of the driverless vehicle, the topological relationship between roads, road width, road length, road shape, number of lanes, lane width, Road attribute information such as lane type, and white solid line, white dashed line, yellow solid line, yellow dashed line, lane stop line, sidewalk, road median, grid line, diamond-shaped deceleration sign, straight arrow, left turn in each road Arrows, right-turn arrows, U-turn arrows, parking spaces and other road marking information;

Step 2. Manually drive the unmanned vehicle to drive in the target area, and use the on-board sensors (lidar and camera) and high-precision integrated positioning system (satellite positioning system and inertial navigation system) to collect raw road data. Among them, the laser radar adopts Velodyne's HDL-64E high-precision laser radar, which is installed in front of the roof; the camera adopts the DFK 23G274 industrial camera of Imaging Company, which is installed on the inside of the windshield and at the position of the rearview mirror; combined positioning The system uses NovAtel's inertial integrated navigation system SPAN-CPT, and the signal receiving antenna of the integrated positioning system is located at the rear of the roof;

Step 3. Use the lidar data and camera data collected by the vehicle to automatically detect the relevant feature information of the road offline, and manually confirm the detection results, remove the false detection results, and complete the missed detection results. The lidar data is used to detect the position and height of the road edge, and the camera data is used to detect the width and color of the lane line. The location and height of the road edge detected offline, the width and color of the lane line and other information will be used as the prior information of the unmanned vehicle to detect the road edge and lane line online during the automatic driving process, thereby improving its detection. Rate;

Step 4. Using the positioning data collected by the vehicle on the target road section, after smoothing by the extended Kalman filter, the jump of the positioning signal is removed, and the driving track of the vehicle on a certain lane is generated. After obtaining the vehicle trajectory, if the unmanned vehicle cannot detect the road edge and lane line under harsh conditions, and cannot accurately match itself to the local map, it can move forward according to the vehicle trajectory. On the other hand, when the vehicle turns at the intersection, it can also refer to the driving track to move forward;

Step 5. Combine the results obtained in Step 1, Step 3, and Step 4 to generate a global offline map. The road attribute information obtained in step 1, the road edge and lane line information obtained in step 3 are used to generate the first layer of the map; the road surface identification information obtained in step 1, and the vehicle trajectory information obtained in step 4 are used to generate the first layer of the map second floor. Data in the second layer of the map is associated with data in the first layer based on its geographic location. Figure 3 is a schematic diagram of a certain area in the offline global map of Hefei. Figure 4 is an enlarged view of an intersection in the offline global map of Hefei;

Step 6. During the automatic driving process of the unmanned vehicle in the target area, the road data in the offline global map is extracted according to the real-time positioning information, and an online local grid map centered on the vehicle is generated. The size of the online partial grid map and the actual size of each grid representation can be defined according to actual needs. In the embodiment of the present invention, the grid map has a width of 500 and a height of 750, where each grid represents a 20cm*20cm square in the actual road scene. The center of the vehicle is located at (250, 500) of the grid map coordinates, so the range of the drawn local grid map is 100 meters in front of the vehicle, 50 meters behind, and 50 meters on the left and right sides.

In a word, the present invention relates to a system and method for generating a lane-level navigation map of unmanned vehicles based on multi-source data, which can be applied to lane-level high-precision positioning and path planning of unmanned vehicles in urban roads. The invention utilizes satellite photos and the vehicle's own sensors to extract road information and generate lane-level navigation maps. The map has three main functions for unmanned vehicles: First, during the process of automatic driving, the vehicle can read the width of the current road, the position and height of the road edge, the width and height of the lane line according to the real-time positioning information. Attribute information such as color, using this as a priori information to further detect road edges and lane lines, and improve the detection rate; second, after detecting the position of road edges and lane lines relative to the vehicle, match with the relevant data in the map , correct the current positioning error, so as to achieve lane-level positioning; third, after the vehicle achieves lane-level positioning, the decision-making system can make lane-level path planning, so that unmanned vehicles can drive according to actual traffic rules, improving It improves the intelligence and comfort of unmanned vehicles.

Parts not described in detail in the present invention belong to the known techniques of those skilled in the art.

The above content is a detailed description of the present invention in conjunction with specific implementation modes, but it cannot be assumed that the specific implementation of the present invention is limited to these content. Without departing from the principle and spirit of the present invention, those skilled in the art can make some adjustments and modifications to these implementations, and the protection scope of the present invention is defined by the appended claims and their equivalents.

Claims (6)

1. A generation system of an unmanned vehicle lane-level navigation map, characterized in that: comprising an offline module and an online module; The offline module uses a variety of data collection methods to obtain the original road data in the target area of the unmanned vehicle, and after offline processing, extracts a variety of road information, and then fuses the extracted results to generate an offline global map; In the online module, during the automatic driving process of the vehicle in the target area, the road data in the offline global map is extracted according to the real-time positioning information, and an online local map centered on the vehicle and within a fixed distance range is drawn. 2. The generating system of a lane-level navigation map for unmanned vehicles according to claim 1, wherein the sources of the original road data in the offline module include: satellite photos or aerial photos, on-board sensors, high-precision Integrated positioning system, vehicle sensors include lidar and camera, high-precision integrated positioning system includes satellite positioning system and inertial navigation system; where satellite photos are used to obtain road topology relationship between roads, road length, number of lanes, lane width road attribute information And lane lines, stop road surface identification information; lidar is used to detect the position and height of the road edge; camera is used to detect the width and color of lane lines; high-precision combined positioning system is used to obtain the position and heading information of the vehicle at a certain moment And the driving trajectory information within a certain period of time. 3. the generation system of a kind of unmanned vehicle lane-level navigation map according to claim 1, is characterized in that: the extraction process of road information in the described off-line module comprises two kinds: The first one is manual extraction using map labeling software; The second is to use algorithms to automatically detect and manually confirm the detection results, remove false detection results, and complete missed detection results. 4. The generation system of a kind of unmanned vehicle lane-level navigation map according to claim 1, is characterized in that: described offline global map adopts layered structure storage, altogether two-layer structure, each layer of data is interrelated, which is: The first layer is road-level navigation information, including road attribute information such as topological relationship between roads, road length, number of lanes, and lane width; The second layer, lane-level navigation information, includes lane attribute information such as various road signs in each road segment, position and height of road edges, width and color of lane lines, and vehicle trajectory information. 5. The generation system of a lane-level navigation map for unmanned vehicles according to claim 1, wherein the online partial map in the online module is a grid map with a width of 500 and a height of 750, wherein each grid Represents a 20cm*20cm square in the actual road scene; the center of the vehicle is located at (250, 500) of the grid map coordinate system, and the range of the drawn local map is 100 meters in front of the vehicle, 50 meters behind, left and right 50 meters each. 6. A method for generating an unmanned vehicle lane-level navigation map, characterized in that: the specific steps of the method are as follows: Step 1. Obtain satellite photos or aerial photos with geographic location information, and manually extract road information on relevant map labeling software. Satellite photos can be obtained for free or purchased from relevant satellite photo providers, and aerial photos can be obtained from relevant Aerial photos purchased from providers or taken by small aerial cameras; map labeling software can be free map software or paid map software, or self-developed satellite map geographic information labeling software; road information to be extracted includes unmanned The starting waypoint and intermediate waypoint of each road in the driving vehicle driving target area, the topological relationship between roads, road width, road length, road shape, number of lanes, lane width, lane type road attribute information, and each white solid line, white dashed line, yellow solid line, yellow dashed line, lane stop line, sidewalk, road median, grid line, diamond-shaped deceleration sign, straight arrow, left turn arrow, right turn arrow, U-turn arrow, Parking space pavement identification information; Step 2. Manually drive the unmanned vehicle to drive in the target area, and use the on-board sensor and high-precision integrated positioning system to collect raw road data. The on-board sensor includes laser radar and camera, and the high-precision integrated positioning system includes satellite positioning system and inertial navigation system. ; Step 3. Use the lidar data and camera data collected by the vehicle to automatically detect the relevant feature information of the road offline, and manually confirm the detection results, remove the false detection results, and complete the missed detection results. The lidar data is used for Detect the position and height of the road edge, and the camera data is used to detect the width and color of the lane line; Step 4. Using the positioning data collected by the vehicle on the target road section, after smoothing with the extended Kalman filter, the jump of the positioning signal is removed, and the driving track of the vehicle on a certain lane is generated; Step 5. Fusion the results obtained in step 1, step 3, and step 4 to generate a global offline map; the road attribute information obtained in step 1, the road edge and lane line information obtained in step 3 are used to generate the first layer of the map The road identification information obtained in step 1 and the vehicle travel track information obtained in step 4 are used to generate the second layer of the map; the data in the second layer of the map is associated with the data in the first layer according to its geographic location; Step 6. During the automatic driving process of the unmanned vehicle in the target area, according to the real-time positioning information, the road data in the offline global map is extracted, and the vehicle is centered, 100 meters in front, 50 meters behind, and 50 meters on the left and right. Online local maps within meters.